High-Resolution Super sampling of BASP-ORCA Contrast Agents in Magnetic Resonance Imaging
JSHS · 2024
Overview
Magnetic Resonance Imaging (MRI) is crucial in clinical diagnostics, but traditional metal-based contrast agents have toxicity concerns. When nearly 1 in 7 Americans suffer from some class of Chronic Kidney Disease traditional contrast agents pose a risk to their health due to heavy metal toxicity. Brush-Arm Star Polymer Organic Radical Contrast Agents (BASP-ORCAs), a new metal-free class, enhance MRI by providing better transverse relaxivity and stability, reducing health risks from conventional agents. The research evaluates deep learning models, specifically convolutional neural networks and hybrid attention transformers, for improving MRI scan resolution. These models are trained on nearly three hundred T1 and T2 MRI images, mainly sourced from the IXI dataset and supplemented with BASP-ORCA scans. Images are downscaled so that they can be trained against their high resolution counter parts. The models are meant to learn complex patterns to enhance image quality. This results in sharper, more detailed images, crucial for tumor detection and characterization. The model achieved a Structural Similarity Index Measure of 0.92 and a Peak Signal-to-Noise Ratio of 33.13, showing its effectiveness. Combining BASP-ORCAs with advanced computational techniques could improve diagnostic accuracy and patient safety, signifying a shift towards non-toxic radiology solutions. Washington
Competition history
- JSHS 2024
Resources
Related projects
ISEF · 2021
Improving Image Contrast in MRI 7T for Early Diagnosis and Disease Detection
ISEF · 2023
Low-Field MRI Super-Resolution With Densely Engineered U-Net++ Network: Improving Resolution and Contrast of Portable MRI With Nested U-Net Architecture, Enabling Low-Cost Bedside Neurological Imaging on a Global Scale
JSHS · 2023
An Accurate Super-Resolution Approach for Low-Field MRIU Imaging via U-Net Network
ISEF · 2019
Fast MRI: Reconstructing MR Images Using Undersampled k-space and a GAN
ISEF · 2014
Computational Simulation of T1 Contrast in BOLD-fMRI Scans to Improve Analysis Potential
ISEF · 2022
An Efficient and Accurate Super-Resolution Approach to Low-Field MRI via U-Net Architecture With Logarithmic Loss and L2 Regularization
ISEF · 2023
Solve Deblurring and Super Resolution in Low-Dose Computer Tomography via One Novel Neural Network
ISEF · 2018
Context Aware Medical Image Super Resolution Using Convolutional Neural Networks
Closest projects by meaning, across every fair and year in the corpus.